Models 模型

Models 模型 Models 模型 Modified September 7, 2024 Models 模型 With Cursor Chat, Ctrl/⌘ K, and Terminal Ctrl/⌘ K, you can easily switch between different models of your choice. 使用光标聊天、Ctrl/⌘ K 和终端 Ctrl/⌘ K，您可以轻松地在您选择的不同模型之间切换。 Model Dropdown 模型下拉列表 Underneath the AI input box, you will see a dropdown that allows you to select the model you want to use. By default, Cursor has these models ready to use: 在 AI 输入框下方，您将看到一个下拉列表，允许您选择要使用的模型。默认情况下，Cursor 已准备好使用这些模型： • GPT 4o GPT 4o • GPT 4 GPT 4 • Claude 3.5 Sonnet • cursor small ◦ cursor small is Cursor’s custom model that isn’t as smart as GPT 4, but is faster and users have unlimited access to it. cursor small 是 Cursor 的自定义模型，它不如 GPT 4 智能，但速度更快，用户可以无限制地访问它。 You can add additional models under Cursor Settings Models Model Names. 您可以在 Cursor Settings Models Model Names 下添加其他模型。 Long Context Only Models 仅长上下文模型 In long context chat, the model selection is limited to the models that support long context: 在长上下文聊天中，模型选择仅限于支持长上下文的模型： • gpt 4o 128k • gemini 1.5 flash 500k • claude 3 haiku 200k • claude 3 sonnet 200k • claude 3 5 sonnet 200k What context window is used for model X? 模型 X 使用什么上下文窗口？ In chat, we limit to around 20,000 tokens at the moment (or less if the model does not support that much context). For cmd K, we limit to around 10,000 tokens, to balance TTFT and quality. Long context chat uses the model’s maximum context window. 在聊天中，我们目前限制在 20,000 个令牌左右（如果模型不支持那么多上下文，则更少）。对于 cmd K，我们限制在 10,000 个左右的 Token，以平衡 TTFT 和质量。长上下文聊天使用模型的最大上下文窗口。 GPT 4o https://openai.com/index/hello gpt 4o/ GPT 4o GPT 4 https://openai.com/index/gpt 4/ GPT 4 https://openai.com/index/gpt 4/ Claude 3.5 Sonnet gpt 4o 128k gemini 1.5 flash 500k claude 3 haiku 200k claude 3 sonnet 200k claude 3 5 sonnet 200k Models 模型 With Cursor Chat, Ctrl/⌘ K, and Terminal Ctrl/⌘ K, you can easily switch between different models of your choice. 使用光标聊天、Ctrl/⌘ K 和终端 Ctrl/⌘ K，您可以轻松地在您选择的不同模型之间切换。 Model Dropdown 模型下拉列表 Underneath the AI input box, you will see a dropdown that allows you to select the model you want to use. By default, Cursor has these models ready to use: 在 AI 输入框下方，您将看到一个下拉列表，允许您选择要使用的模型。默认情况下，Cursor 已准备好使用这些模型： • GPT 4o GPT 4o GPT 4o https://openai.com/index/hello gpt 4o/ GPT 4o • GPT 4 GPT 4 GPT 4 https://openai.com/index/gpt 4/ GPT 4 https://openai.com/index/gpt 4/ • Claude 3.5 Sonnet Claude 3.5 Sonnet • cursor small ◦ cursor small is Cursor’s custom model that isn’t as smart as GPT 4, but is faster and users have unlimited access to it. cursor small 是 Cursor 的自定义模型，它不如 GPT 4 智能，但速度更快，用户可以无限制地访问它。 ◦ cursor small is Cursor’s custom model that isn’t as smart as GPT 4, but is faster and users have unlimited access to it. cursor small 是 Cursor 的自定义模型，它不如 GPT 4 智能，但速度更快，用户可以无限制地访问它。 You can add additional models under Cursor Settings Models Model Names. 您可以在 Cursor Settings Models Model Names 下添加其他模型。 Long Context Only Models 仅长上下文模型 In long context chat, the model selection is limited to the models that support long context: 在长上下文聊天中，模型选择仅限于支持长上下文的模型： • gpt 4o 128k gpt 4o 128k • gemini 1.5 flash 500k gemini 1.5 flash 500k • claude 3 haiku 200k claude 3 haiku 200k • claude 3 sonnet 200k claude 3 sonnet 200k • claude 3 5 sonnet 200k claude 3 5 sonnet 200k What context window is used for model X? 模型 X 使用什么上下文窗口？ In chat, we limit to around 20,000 tokens at the moment (or less if the model does not support that much context). For cmd K, we limit to around 10,000 tokens, to balance TTFT and quality. Long context chat uses the model’s maximum context window. 在聊天中，我们目前限制在 20,000 个令牌左右（如果模型不支持那么多上下文，则更少）。对于 cmd K，我们限制在 10,000 个左右的 Token，以平衡 TTFT 和质量。长上下文聊天使用模型的最大上下文窗口。